Notebooks in Gemini vs Spectrum

Google has launched Notebooks in Gemini, a new organizational layer that groups related chats, files, and project context into a single persistent workspace. Unlike standard Gemini conversations that exist in isolation, Notebooks let users create project-scoped containers — similar in spirit to Claude's Projects feature — where AI context, uploaded documents, and conversation history persist and accumulate over time. The feature integrates with Google Workspace, allowing users to attach Google Docs, Sheets, Drive files, and Gmail threads directly to a Notebook. Gemini can then be queried across all attached materials in a unified way, making it useful for long-running research, client projects, or any work that spans multiple sessions and document types. Notebooks debuted at #2 on Product Hunt with 181 upvotes on launch day. This positions Gemini more directly against Claude's Projects and ChatGPT's memory-augmented workspaces. For Google Workspace users in particular, the tight Drive and Docs integration gives Notebooks a material advantage — it's the only AI workspace with native access to the full Google productivity stack. Enterprise buyers who've already committed to Workspace will find the feature immediately useful without any additional setup.

Spectrum, from Photon, launched on Product Hunt today with 105 upvotes and a simple but sharp premise: your users don't want to learn a new AI interface—they want AI to show up in Slack, Teams, email, and every other tool they already use. Spectrum is an agent deployment layer that routes your AI agents to wherever your users are, with no per-integration custom dev work. The core product is an abstraction layer that handles the connector plumbing: authenticate once, and your agent can receive messages and send responses across all connected channels. Built-in conversation management means agents maintain context across channels—a user can start a request in Slack, continue it in Teams, and finish in email without losing thread. The platform also handles rate limiting, authentication, and error handling for each channel. For teams building internal AI tools or customer-facing AI assistants, this solves real integration pain. Building a Slack bot, Teams integration, email handler, and web widget separately takes weeks per channel. Spectrum reduces that to a single agent definition deployed everywhere. The question is pricing and lock-in: if Photon becomes the integration layer, they sit in a strategically critical position.